000			03774nam a2200433 i 4500
999			_c387986 _d387986
001			387986
003			ES-MaUEC
005			20230613095712.0
006			a||||fo|||| 00| 0
007			cr nn 008mamaa
008			220606s2022 sz | o |||| 0|eng d
020			_a9783031791758
024	7		_a10.1007/978-3-031-79175-8 _2doi
040			_aES-MaUEC _bspa _cES-MaUEC _dES-MaUEC
050		4	_aTA1634 _b2022 EB
100	1		_aCsurka, Gabriela _eautor _4aut _4http://id.loc.gov/vocabulary/relators/aut _9688398
245	1	0	_aVisual Domain Adaptation in the Deep Learning Era _cby Gabriela Csurka, Timothy M. Hospedales, Mathieu Salzmann, Tatiana Tommasi
250			_a1st edition 2022
264		1	_aCham _bSpringer International Publishing _c2022
300			_a1 recurso en línea (IV, 190 páginas)
336			_aTexto _btxt _2rdacontent
337			_aelectrónico _bc _2rdamedia
338			_arecurso electrónico _bcr _2rdacarrier
347			_aarchivo de texto _bPDF
490	0		_aSynthesis Lectures on Computer Vision _x2153-1064
520			_aSolving problems with deep neural networks typically relies on massive amounts of labeled training data to achieve high performance. While in many situations huge volumes of unlabeled data can be and often are generated and available, the cost of acquiring data labels remains high. Transfer learning (TL), and in particular domain adaptation (DA), has emerged as an effective solution to overcome the burden of annotation, exploiting the unlabeled data available from the target domain together with labeled data or pre-trained models from similar, yet different source domains. The aim of this book is to provide an overview of such DA/TL methods applied to computer vision, a field whose popularity has increased significantly in the last few years. We set the stage by revisiting the theoretical background and some of the historical shallow methods before discussing and comparing different domain adaptation strategies that exploit deep architectures for visual recognition. We introduce the space of self-training-based methods that draw inspiration from the related fields of deep semi-supervised and self-supervised learning in solving the deep domain adaptation. Going beyond the classic domain adaptation problem, we then explore the rich space of problem settings that arise when applying domain adaptation in practice such as partial or open-set DA, where source and target data categories do not fully overlap, continuous DA where the target data comes as a stream, and so on. We next consider the least restrictive setting of domain generalization (DG), as an extreme case where neither labeled nor unlabeled target data are available during training. Finally, we close by considering the emerging area of learning-to-learn and how it can be applied to further improve existing approaches to cross domain learning problems such as DA and DG.
988			_aSynthesis Collection of Technology_2022
650		7	_2embne _9159793 _aVisión por ordenador
700	1		_aHospedales, Timothy M. _eautor _4aut _4http://id.loc.gov/vocabulary/relators/aut _9688399
700	1		_aSalzmann, Mathieu _eautor _4aut _4http://id.loc.gov/vocabulary/relators/aut _9688400
700	1		_aTommasi, Tatiana _eautor _4aut _4http://id.loc.gov/vocabulary/relators/aut _9688401
776	0	8	_iPrinted edition: _z9783031791802
776	0	8	_iPrinted edition: _z9783031791703
776	0	8	_iPrinted edition: _z9783031791857
856	4	0	_uhttps://go.openathens.net/redirector/universidadeuropea.es?url=https://doi.org/10.1007/978-3-031-79175-8 _zAcceso a este recurso digital (usuarios Universidad Europea de Madrid)
942			_2lcc _cLE
998			_b05/2023 _dz _eb _zSI